I have been wondering for a while why Economists haven’t made better use of Google keyword search analytics as an economic tool after hearing how Google can predict flu outbreaks with surprising accuracy:
While Google flu trends is a coarse indicator, I wondered if other Google search terms could be more accurate short-term predictors of patterns. Then I recently came across this article:
Which got me thinking about a conversation I had with a nephew-in-law, a Cambridge-trained Economist who works for Google in London. He mentioned in August that Google examines certain search terms that are diagnostic for a country’s economic performance all the time (in order to target marketing campaigns, for example) and that their prediction algorithms were forecasting Germany’s economy going in to recession. Two weeks later a Financial Times article stated that the latest economic indicators confirmed that Germany’s economy had shrunk for the past two quarters, the official definition of a recession.
Then I heard this recent article about Facebook “likes” being accurate predictors of a company’s stock price:
How useful is “Sentiment Analysis” to the prediction and analysis of economic trends, theories and predictions? Some interesting academic publications suggest a rich future for this technology:
Twitter has the capacity to provide real-time sentiment analysis, a fact not lost on consumer brands that rely on customer feedback to engage customers in a variety of ways:
Academic and commercial research into Twitter also suggests how real-time aggregate feeds can lead to better predictions of economic trends:
Is this the future of hedge-funds and options trading? Apparently a number of hedge funds think so: